Automated Annotation with Generative AI Requires Validation
This addresses the challenge for researchers in social science and other fields who use LLMs for annotation, but it is incremental as it builds on existing validation practices.
The study tackled the problem of variable performance in using generative large language models (LLMs) for automated text annotation, finding that LLM performance is promising but highly contingent on dataset and task type, reinforcing the need for task-by-task validation.
Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty. Because these challenges will persist even as LLM technology improves, we argue that any automated annotation process using an LLM must validate the LLM's performance against labels generated by humans. To this end, we outline a workflow to harness the annotation potential of LLMs in a principled, efficient way. Using GPT-4, we validate this approach by replicating 27 annotation tasks across 11 datasets from recent social science articles in high-impact journals. We find that LLM performance for text annotation is promising but highly contingent on both the dataset and the type of annotation task, which reinforces the necessity to validate on a task-by-task basis. We make available easy-to-use software designed to implement our workflow and streamline the deployment of LLMs for automated annotation.